© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 62416
    Prev
    Next
    INDEX
    Explanations

    expressions related to abstract concepts and objects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code fragments and outputs from context-free grammar systems that generate random sentences by replacing placeholder tokens with predefined production rules.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -Allow
    -0.08
    -fontawesome
    -0.07
    yles
    -0.06
    ennie
    -0.06
    mini
    -0.06
     strSql
    -0.06
    decess
    -0.06
    179
    -0.06
    intestinal
    -0.06
    211
    -0.06
    POSITIVE LOGITS
    ütün
    0.08
    ÏĦεÏģ
    0.08
    кап
    0.08
     zbo
    0.08
    ,eg
    0.07
    èo
    0.07
    ưá»Ŀng
    0.07
    ằ
    0.07
    á»±
    0.07
    _________________↵↵
    0.07
    Activations Density 0.021%

    No Known Activations